Table of Content

Open Access

ARTICLE

Nonlinear Activation Functions in CNN Based on Fluid Dynamics and Its Applications

Kazuhiko Kakuda1,*, Tomoyuki Enomoto1, Shinichiro Miura2
Department of Mathematical Information Engineering, College of Industrial Technology, Nihon University, Chiba 275-8575, Japan.
Department of Liberal Arts and Basic Sciences, College of Industrial Technology, Nihon University, Chiba 275-8576, Japan.
* Corresponding Author: Kazuhiko Kakuda. Email: .

Computer Modeling in Engineering & Sciences 2019, 118(1), 1-14. https://doi.org/10.31614/cmes.2019.04676

Abstract

The nonlinear activation functions in the deep CNN (Convolutional Neural Network) based on fluid dynamics are presented. We propose two types of activation functions by applying the so-called parametric softsign to the negative region. We use significantly the well-known TensorFlow as the deep learning framework. The CNN architecture consists of three convolutional layers with the max-pooling and one fully-connected softmax layer. The CNN approaches are applied to three benchmark datasets, namely, MNIST, CIFAR-10, and CIFAR-100. Numerical results demonstrate the workability and the validity of the present approach through comparison with other numerical performances.

Keywords

Deep learning, CNN, activation function, fluid dynamics, MNIST, CIFAR-10, CIFAR-100.

Cite This Article

Kakuda, K., Enomoto, T., Miura, S. (2019). Nonlinear Activation Functions in CNN Based on Fluid Dynamics and Its Applications. CMES-Computer Modeling in Engineering & Sciences, 118(1), 1–14.



This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 2889

    View

  • 1169

    Download

  • 0

    Like

Share Link

WeChat scan